In this paper, we present a novel Multi-Objective Ant Colony System algorithm to optimize Cost, Performance, and Reliability (MOACS-CoPeR) in the cloud. The proposed algorithm provides a metaheuristic-based approach f...
详细信息
ISBN:
(纸本)9780769556970
In this paper, we present a novel Multi-Objective Ant Colony System algorithm to optimize Cost, Performance, and Reliability (MOACS-CoPeR) in the cloud. The proposed algorithm provides a metaheuristic-based approach for the multi-objective cloud-based software component deployment problem. MOACS-CoPeR explores the search-space of architecture design alternatives with respect to several architectural degrees of freedom and produces a set of Pareto-optimal deployment configurations. We also present a Java-based implementation of our proposed algorithm and compare its results with the Non-dominated Sorting Genetic Algorithm II (NSGA-II). We evaluate the two algorithms against a cloud-based storage service, which is loosely based on a real system.
The communication between hardware components in embedded systems is steadily growing as more and more software functions are necessary to fulfill the requirements of modern systems, like cars in the automotive area. ...
详细信息
ISBN:
(纸本)9781509047932
The communication between hardware components in embedded systems is steadily growing as more and more software functions are necessary to fulfill the requirements of modern systems, like cars in the automotive area. As a result, the capacity of the communication transport system is quickly exceeded. Besides the possibility to exchange the physical connection, another one is to analyze the system and e.g. reallocate the functions in order to reduce the communication overhead. In this paper, an approach is presented which is based on the idea of redundancy, however, not in the sense of reliability, but to create solutions where software functions of are duplicated and allocated to other hardware components additionally. The approach is demonstrated on a real-world problem instance with functions of a plug-in electric driven vehicle, where an existing implementation serves as reference during the optimization, and other public problem instances. Results show that further improvements, in comparison to the optimization without redundancy, are achieved that require only a few duplicates to reduce the communication between hardware components.
暂无评论